BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Australian Data Science Network - ECPv6.16.5.1//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://australiandatascience.net
X-WR-CALDESC:Events for Australian Data Science Network
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Australia/Brisbane
BEGIN:STANDARD
TZOFFSETFROM:+1000
TZOFFSETTO:+1000
TZNAME:AEST
DTSTART:20200101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Australia/Brisbane:20210714T100000
DTEND;TZID=Australia/Brisbane:20210719T104500
DTSTAMP:20211026T024210Z
CREATED:20210709T023716Z
LAST-MODIFIED:20211026T024210Z
UID:2221-1626256800-1626691500@australiandatascience.net
SUMMARY:AI4Pandemics Talk #1: Chris Rackauckas\, MIT
DESCRIPTION:The first AI4PAN seminar speaker will be Chris Rackauckas (MIT) \nYouTube Recording \nTitle: \nLearning Epidemic Models That Extrapolate. \nAbstract: \nModern techniques of machine learning are uncanny in their ability to automatically learn predictive models directly from data. However\, they do not tend to work beyond their original training dataset. Mechanistic models utilize characteristics of the problem to ensure accurate qualitative extrapolation but can lack in predictive power. How can we build techniques which integrate the best of both approaches? In this talk we will discuss the body of work around universal differential equations\, a technique which mixes traditional differential equation modeling with machine learning for accurate extrapolation from small data. We will showcase how incorporating different variations of the technique\, such as Bayesian symbolic regression and optimizing the choice of architectures\, can lead to the recovery of predictive epidemic models in a robust way. The numerical difficulties of learning potentially stiff and chaotic models will highlight how most of the adjoint techniques used throughout machine learning are inappropriate for learning scientific models\, and techniques which mitigate these numerical ills will be demonstrated. We end by showing how these improved stability techniques have been automated and optimized by the software of the SciML organization\, allowing practitioners to quickly scale these techniques to real-world applications. \n\n 
URL:https://australiandatascience.net/event/ai4pan-seminar-series-with-chris-rackauckas-mit/
LOCATION:Zoom
CATEGORIES:Seminar
ORGANIZER;CN="Hamid Khataee":MAILTO:h.khataee@uq.edu.au
END:VEVENT
END:VCALENDAR